Representing Piecewise Linear Functions by Functions with Small Arity
Not on the map. Why?
Abstract (arXiv)
A piecewise linear function can be described in different forms: as an arbitrarily nested expression of min- and max-functions, as a difference of two convex piecewise linear functions, or as a linear combination of maxima of affine-linear functions. In this paper, we provide two main results: first, we show that for every piecewise linear function there exists a linear combination of max-functions with at most n+1 arguments, and give an algorithm for its computation. Moreover, these arguments are contained in the finite set of affine-linear functions that coincide with the given function in some open set. Second, we prove that the piecewise linear function max(0, x1, ldots, xn) cannot be represented as a linear combination of maxima of less than n+1 affine-linear arguments. This was conjectured by Wang and Sun in 2005 in a paper on representations of piecewise linear functions as linear combination of maxima.
Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 4 of its 16 references that are in the map. First posted on arXiv 26 May 2023.
Builds on
4 of 16 references.
References · 4
- 2016Understanding Deep Neural Networks with Rectified Linear Unitscited by 253
- 2021Towards Lower Bounds on the Depth of ReLU Neural Networkscited by 55
- 2021Sharp bounds for the number of regions of maxout networks and vertices of Minkowski sumscited by 37
- 2021Novel convex decomposition of piecewise affine functionscited by 4
Built on by
Citing papers per year: 2024: 3; 2025: 2; 2026: 2.
7 papers.
- 2024Decomposition Polyhedra of Piecewise Linear Functionscited by 9
- 2024Representing Piecewise-Linear Functions by Functions with Minimal Aritycited by 2
- 2026Shallower ReLU Network Representations via Exact Linear Algebracited by 2
- 2024The Topos of Transformer Networkscited by 1
- 2025Linear-Size Neural Network Representation of Piecewise Affine Functions in ℝ2cited by 1
- 2025On the expressivity of sparse maxout networkscited by 0
- 2026Hidden Monotonicity: Explaining Deep Neural Networks via their DC Decompositioncited by 0
- 2026Shallower ReLU Network Representations via Exact Linear Algebra22 Jul 2026
- 2026Hidden Monotonicity: Explaining Deep Neural Networks via their DC Decomposition12 Jan 2026
- 2025On the expressivity of sparse maxout networks15 Oct 2025
- 2025Linear-Size Neural Network Representation of Piecewise Affine Functions in ℝ217 Mar 2025
- 2024Decomposition Polyhedra of Piecewise Linear Functions7 Oct 2024
- 2024Representing Piecewise-Linear Functions by Functions with Minimal Arity4 Jun 2024
- 2024The Topos of Transformer Networks27 Mar 2024